import gradio as gr
import pandas as pd
from smolagents import CodeAgent, OpenAIServerModel, tool
import os, subprocess
from bs4 import BeautifulSoup
from duckduckgo_search import DDGS
import csv
import json
import requests
import whisper
from typing import Optional
import openpyxl

# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

# --- Basic Agent Definition ---
# ----- THIS IS WHERE YOU CAN BUILD WHAT YOU WANT ------
def download_file(file_name: str) -> None:
    if not os.path.exists(file_name):
        url = f"{DEFAULT_API_URL}/files/{file_name.split('.')[0]}"
        r = requests.get(url)
        with open(file_name, "wb") as f:
            f.write(r.content)

@tool
def open_file_as_text(file_name: str, filetype: Optional[str] = "txt") -> str:
    """
    Opens a file and returns its content as readable text.
    Supports 'txt', 'json', 'csv', 'xlsx', and 'mp3' (transcribes speech to text).
    Args:
        file_name (str): The path or name of the file.
        filetype (Optional[str]): Type of file ('txt', 'json', 'csv', 'xlsx', 'mp3'). Defaults to 'txt'.
    Returns:
        str: The content of the file as text, or transcribed speech if 'mp3'.
    """
    download_file(file_name)
    try:
        if filetype == "txt":
            with open(file_name, "r", encoding="utf-8") as f:
                return f.read()

        elif filetype == "json":
            with open(file_name, "r", encoding="utf-8") as f:
                data = json.load(f)
            return json.dumps(data, indent=2)

        elif filetype == "csv":
            with open(file_name, "r", encoding="utf-8") as f:
                reader = csv.reader(f)
                rows = list(reader)
            return "\n".join([", ".join(row) for row in rows])

        elif filetype == "xlsx":
            wb = openpyxl.load_workbook(file_name, data_only=True)
            sheet = wb.active
            content = []
            for row in sheet.iter_rows(values_only=True):
                content.append(", ".join(str(cell) if cell is not None else "" for cell in row))
            return "\n".join(content)

        elif filetype == "mp3":
            w = whisper.load_model("base")
            res = w.transcribe(file_name)
            return res["text"]

        else:
            return f"Unsupported filetype '{filetype}'. Supported types are 'txt', 'json', 'csv', 'xlsx', and 'mp3'."

    except FileNotFoundError:
        return f"File '{file_name}' not found."
    except Exception as e:
        return f"Error opening file '{file_name}': {str(e)}"

@tool
def web_search(query: str) -> str:
    """
    Searches the web using DuckDuckGo and returns top search snippets.
    Args:
        query (str): The search query string.
    Returns:
        str: A list of top search results with title, snippet, and URL.
    """
    try:
        with DDGS() as ddgs:
            results = ddgs.text(query, max_results=3)
            if not results:
                return "No results found."
            return "\n\n".join([f"Title: {r['title']}\nSnippet: {r['body']}\nURL: {r['href']}" for r in results])
    except Exception as e:
        return f"Error during search: {str(e)}"

def parse_wikipedia_table(table) -> str:
    """
    Parses a Wikipedia table into a clean, readable text format.
    Args:
        table (Tag): BeautifulSoup Tag for the table.
    Returns:
        str: Formatted table as readable text.
    """
    rows = []
    headers = []

    # Try to get headers
    thead = table.find('thead')
    if thead:
        for th in thead.find_all('th'):
            header_text = th.get_text(separator=" ", strip=True)
            headers.append(header_text)
        if headers:
            rows.append(" | ".join(headers))

    # Parse table body rows
    tbody = table.find('tbody')
    if not tbody:
        tbody = table  # fallback: some tables have no tbody explicitly

    for tr in tbody.find_all('tr'):
        cells = tr.find_all(['th', 'td'])
        cell_texts = []
        for cell in cells:
            # Clean references like [7], [note 1], etc.
            for sup in cell.find_all('sup', class_='reference'):
                sup.decompose()

            text = cell.get_text(separator=" ", strip=True)
            cell_texts.append(text)

        if cell_texts:
            row_text = " | ".join(cell_texts)
            rows.append(row_text)

    return "\n".join(rows)

@tool
def read_wikipedia_page(url: str) -> str:
    """
    Fetches a Wikipedia article and extracts clean sectioned text around the relevant query.
    Args:
        url (str): The Wikipedia page URL.
    Returns:
        str: Sectioned and readable snippet focused around the query.
    """
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36"
    }
    resp = requests.get(url, headers=headers, timeout=10)
    resp.raise_for_status()
    soup = BeautifulSoup(resp.text, "html.parser")

    content_div = soup.find('div', id='mw-content-text')
    if not content_div:
        return "Content not found."

    parts = []
    for elem in content_div.find_all(['h2', 'h3', 'p', 'ul', 'ol', 'table']):
        if elem.name in ['h2', 'h3']:
            parts.append("\n\n" + elem.get_text(strip=True) + "\n")
        elif elem.name in ['p', 'ul', 'ol']:
            parts.append(elem.get_text(strip=True))
        elif elem.name == 'table':
            parts.append(parse_wikipedia_table(elem))

    full_text = "\n".join(parts)

    return full_text

@tool
def smart_paginate_around_query(full_text: str, query: str) -> list:
    """
    Splits text into windows around each occurrence of the query.
    Args:
        full_text (str): The full text to search within.
        query (str): The search query.
    Returns:
        list: List of relevant text windows (pages).
    """
    before_chars = 1000
    after_chars = 3000
    full_text_lower = full_text.lower()
    query_lower = query.lower()
    query_len = len(query_lower)

    pages = []
    search_pos = 0
    text_len = len(full_text)

    while True:
        match_pos = full_text_lower.find(query_lower, search_pos)

        if match_pos == -1:
            break  # no more matches

        # Define window around match
        start = max(0, match_pos - before_chars)
        end = min(text_len, match_pos + query_len + after_chars)

        page = full_text[start:end]
        pages.append(page)

        # Move search pointer to AFTER current window
        search_pos = end

    return pages

@tool
def reverse_sentence(text: str) -> str:
    """
    Reverses the input text.
    Args:
        text (str): The input string to be reversed.
    Returns:
        str: The reversed string.
    """
    return text[::-1]

@tool
def run_python_code(file_name: str) -> str:
    """
    Executes a Python file and returns its printed final output.
    Args:
        file_name (str): Name of the Python file.
    Returns:
        str: The final printed output.
    """
    download_file(file_name)

    try:
        # Run in subprocess with timeout
        result = subprocess.run(
            ["python", file_name],
            capture_output=True,
            text=True,
            timeout=10  # seconds
        )

        if result.returncode != 0:
            return f"Error running code: {result.stderr.strip()}"

        output = result.stdout.strip()
        return output

    except subprocess.TimeoutExpired:
        return "Execution timed out."
    except Exception as e:
        return f"Error: {str(e)}"

tools = [
    open_file_as_text,
    web_search,
    read_wikipedia_page,
    smart_paginate_around_query,
    reverse_sentence,
]

model = OpenAIServerModel(
    model_id="gpt-4o",
    api_key=os.getenv("OPENAI_API_KEY"),
    temperature=0
)

agent = CodeAgent(
    model=model,
    tools=tools,
    additional_authorized_imports=["pandas", "numpy", "datetime", "json", "re", "math", "os", "requests", "csv", "urllib"]
)

def run_and_submit_all( profile: gr.OAuthProfile | None):
    """
    Fetches all questions, runs the BasicAgent on them, submits all answers,
    and displays the results.
    """
    # --- Determine HF Space Runtime URL and Repo URL ---
    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code

    if profile:
        username= f"{profile.username}"
        print(f"User logged in: {username}")
    else:
        print("User not logged in.")
        return "Please Login to Hugging Face with the button.", None

    api_url = DEFAULT_API_URL
    questions_url = f"{api_url}/questions"
    submit_url = f"{api_url}/submit"

    # 1. Instantiate Agent ( modify this part to create your agent)
    try:
        agent = CodeAgent(
            model=model,
            tools=tools,
            additional_authorized_imports=["pandas", "numpy", "datetime", "json", "re", "math", "os", "requests", "csv",
                                           "urllib"]
        )
    except Exception as e:
        print(f"Error instantiating agent: {e}")
        return f"Error initializing agent: {e}", None
    # In the case of an app running as a hugging Face space, this link points toward your codebase (useful for others so please keep it public)
    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    print(agent_code)

    # 2. Fetch Questions
    print(f"Fetching questions from: {questions_url}")
    try:
        response = requests.get(questions_url, timeout=15)
        response.raise_for_status()
        questions_data = response.json()
        if not questions_data:
             print("Fetched questions list is empty.")
             return "Fetched questions list is empty or invalid format.", None
        print(f"Fetched {len(questions_data)} questions.")
    except requests.exceptions.RequestException as e:
        print(f"Error fetching questions: {e}")
        return f"Error fetching questions: {e}", None
    except requests.exceptions.JSONDecodeError as e:
         print(f"Error decoding JSON response from questions endpoint: {e}")
         print(f"Response text: {response.text[:500]}")
         return f"Error decoding server response for questions: {e}", None
    except Exception as e:
        print(f"An unexpected error occurred fetching questions: {e}")
        return f"An unexpected error occurred fetching questions: {e}", None

    # 3. Run your Agent
    results_log = []
    answers_payload = []
    print(f"Running agent on {len(questions_data)} questions...")
    for item in questions_data:
        task_id = item.get("task_id")
        question_text = item.get("question")
        file_name = item.get("file_name")
        if not task_id or question_text is None:
            print(f"Skipping item with missing task_id or question: {item}")
            continue
        try:
            full_prompt = f"""You are a highly precise answering agent.
When given a question:
- If necessary, perform a web search using the tool `web_search` to find possible sources of information.
- If the web search only returns titles and short snippets, you MUST visit the actual webpage to read the full content before answering.
- Use the `read_wikipedia_page` tool to fetch and read the Wikipedia page when necessary.
- You just have the ability to read Wikipedia pages only.
- You MUST paginate the content using `smart_paginate_around_query`.
- When using `smart_paginate_around_query`, you must select a short, general query based on the main keywords only. Avoid using full questions or long phrases. Use 1–3 essential words. 
- If the task requires reversing the order of words, letters, phrases, or any text, you must use the `reverse_sentence` tool to perform the operation.
- Never reverse text manually inside your code. Always call the tool instead.
- If the task requires reading, listening, or analyzing a file, you must use the file specified in the `file_name` field of the task metadata, not the file name mentioned casually inside the question text.
- Comma separated lists MUST contain a single space after each comma.
- If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise.
- If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise.
- If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
- Only answer after you have gathered enough information by reading the actual page contents.
- Once you have the final answer, you must call `final_answer("your_answer")` immediately after printing it.
- Do not retry or execute anything else after calling `final_answer`.
- `final_answer` must wrap the exact printed value.
Provide ONLY the precise answer requested. 
Do not include explanations, steps, reasoning, or additional text. 
Be direct and specific. GAIA benchmark requires exact matching answers.
Example: if asked "What is the capital of France?", respond exactly:
Thoughts: I need to retrieve the capital of France from Wikipedia and output it directly.
Code:
```py
print("Paris")
```<end_code>
Based on the above guidelines, answer the following question:
--begin of question--
{question_text}
--end of question--
If the questions mentions the need to use a file, use the following `file_name` value as the `file_name` parameter in any function calls:
file_name: {file_name}"""
            submitted_answer = agent.run(full_prompt)
            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
        except Exception as e:
             print(f"Error running agent on task {task_id}: {e}")
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})

    if not answers_payload:
        print("Agent did not produce any answers to submit.")
        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)

    # 4. Prepare Submission 
    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
    print(status_update)

    # 5. Submit
    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
    try:
        response = requests.post(submit_url, json=submission_data, timeout=60)
        response.raise_for_status()
        result_data = response.json()
        final_status = (
            f"Submission Successful!\n"
            f"User: {result_data.get('username')}\n"
            f"Overall Score: {result_data.get('score', 'N/A')}% "
            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
            f"Message: {result_data.get('message', 'No message received.')}"
        )
        print("Submission successful.")
        results_df = pd.DataFrame(results_log)
        return final_status, results_df
    except requests.exceptions.HTTPError as e:
        error_detail = f"Server responded with status {e.response.status_code}."
        try:
            error_json = e.response.json()
            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
        except requests.exceptions.JSONDecodeError:
            error_detail += f" Response: {e.response.text[:500]}"
        status_message = f"Submission Failed: {error_detail}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.Timeout:
        status_message = "Submission Failed: The request timed out."
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.RequestException as e:
        status_message = f"Submission Failed: Network error - {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except Exception as e:
        status_message = f"An unexpected error occurred during submission: {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df


# --- Build Gradio Interface using Blocks ---
with gr.Blocks() as demo:
    gr.Markdown("# Basic Agent Evaluation Runner")
    gr.Markdown(
        """
        **Instructions:**
        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
        ---
        **Disclaimers:**
        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
        """
    )

    gr.LoginButton()

    run_button = gr.Button("Run Evaluation & Submit All Answers")

    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
    # Removed max_rows=10 from DataFrame constructor
    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)

    run_button.click(
        fn=run_and_submit_all,
        outputs=[status_output, results_table]
    )

if __name__ == "__main__":
    print("\n" + "-"*30 + " App Starting " + "-"*30)
    # Check for SPACE_HOST and SPACE_ID at startup for information
    space_host_startup = os.getenv("SPACE_HOST")
    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup

    if space_host_startup:
        print(f"✅ SPACE_HOST found: {space_host_startup}")
        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
    else:
        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")

    if space_id_startup: # Print repo URLs if SPACE_ID is found
        print(f"✅ SPACE_ID found: {space_id_startup}")
        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
    else:
        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")

    print("-"*(60 + len(" App Starting ")) + "\n")

    print("Launching Gradio Interface for Basic Agent Evaluation...")
    demo.launch(debug=True, share=False)